ABSTRACT
This paper presents a semiautomatic method for generating commonsense axioms. The method relies on three metarules that process a few commonsense rules referring to some concept properties. The proposed algorithm searches automatically in Extended WordNet for all concepts that have a given property and generates axioms linking those concepts with the seed commonsense rule. The results show that using 27 commonsense rules, the algorithm generated 2596 axioms of which 98% were validated by human. The generation of commonsense axioms is useful to many natural language applications that require reasoning.
- Luis von Ahn, Mihir Kedia and Manuel Blum. 2006. Verbosity: A Game for Collecting Common-Sense Knowledge. ACM Conference on Human Factors Computing Systems, CHI Notes 2006. Pages 75--78. Google ScholarDigital Library
- I. Dagan, O. Glickman, and B. Magnini. The PASCAL Recognising Textual Entailment Challenge. In Quiño-nero-Candela, J.; Dagan, I.; Magnini, B.; d'Alché-Buc, F. (Eds.) Machine Learning Challenges. Lecture Notes in Computer Science, Vol. 3944, pp. 177--190, Springer, 2006. Google ScholarDigital Library
- A. Fowler, B. Hauser, D. Hodges, I. Niles, A. Novischi, J. Stephan. "Applying COGEX to Recognize Textual Entailment". Machine Learning Challenges. Lecture Notes in Computer Science, Vol. 3944, pp. 177--190, Springer, 2006. Google ScholarDigital Library
- F. Gomez. 2008. The Acquisition of Common Sense Knowledge by Being Told: An Application of NLP to Itself. Lecture Notes in Computer Science, Vol. 5039/2008, Springer/Heidelberg. Google ScholarDigital Library
- J. He, H. Lai, H. Wang 2008. A Cyc-based Multi-agent System. Proceedings of the 41st Hawaii International Conference on System Sciences. Google ScholarDigital Library
- J.R. Hobbs, 1983. Ontological Promiscuity. In Proceedings of the 23rd Annual meeting of Association of Computational Linguistics. Pages 57--63. Cambridge MA. 1983. Google ScholarDigital Library
- D. B. Lenat. 1995. CYC: Large-Scale Investment in Knowledge Infrastructure. Communications of the ACM , vol.38, no 11, 1995. 38(11):28--32. Google ScholarDigital Library
- H. Liu, P. Singh. 2004. ConceptNet--a practical commonsense reasoning toot-kit. BT Technology Journal, vol.22, no 4, October 2004. 22(4):211--226. Google ScholarDigital Library
- G. Miller. 1995. CWordNet: a lexical database. Communications of the ACM, vol.38, no 11, 1995. 38(11):39--41. Google ScholarDigital Library
- Mindpixel Project: http://www.mindpixel.orgGoogle Scholar
- P. Singh, M. Minsky, and I. Eslick. 2004. Computing commonsense. BT Technology Journal, vol.22, no 4, October 2004. 22(4):201--210. Google ScholarDigital Library
- P. Singh, T. Lin, E. T. Mueller, G. Lim, T. Perkins, W. L. Zhu. 2002. Open Mind Commons Sense: Knowledge Acquisition from the general public. Proceedings of the First International Conference on Ontologies, Databases, and Applications of Semantics for Large Scale Informtion Systems, Lecture Notes in Computer Science, No 2519, Heidelbergerg, Springer-Verlag (2002). Google ScholarDigital Library
- V. C. Storey, V. Sugumaran, Y. Ding. 2005. A Semiautomatic Approach to Extracting Common Sense Knowledge from Knowledge Sources, Lecture Notes in Computer Science, Vol. 3513/2005, Springer/Heidelberg. Google ScholarDigital Library
- The Open Mind Common Sense Project: http://www.kurzweilai.net/articles/art0371.htmlGoogle Scholar
- Y. Zhui, L-J. Zang; D-S. Wang, C-G. Cao. 2008. A Manual Experiment on Commonsense Knowledge Acquisition from Web Corpora. Int. Conf. on Machine Learning and Cybernetics, Vol 3.Google Scholar
- XWNproject} The Extended WordNet Project, http://xwn.hlt.utdallas.edu/Google Scholar
Index Terms
- Method for extracting commonsense knowledge
Recommendations
A Property-Based Method for Acquiring Commonsense Knowledge
Knowledge Science, Engineering and ManagementAbstractCommonsense knowledge is crucial in a variety of AI applications. However, one kind of commonsense knowledge that has not received attention is that of properties of actions denoted by verbs. To address this limitation, we propose an approach to ...
Sweet Apple, company? or food? Adjective-centric commonsense knowledge acquisition with taxonomy-guided induction
AbstractHow to enable intelligent machines to possess human commonsense knowledge is one of the central concerns of artificial intelligence. Consequently, a series of commonsense knowledge bases have been designed and constructed by scholars. However, as ...
CoolGust: knowledge representation learning with commonsense knowledge guidelines and constraints
AbstractRepresentation learning serves as a crucial link between knowledge graphs and neural models. Knowledge graphs are typical symbolic models and require representation learning to obtain vector representations of entities and relationships. Existing ...
Comments